arXiv AI September 2, 2026 By Jingcheng Yu, Mingliang Zeng, Qiwei Ye

FloydNet: A Learning Paradigm for Global Relational Reasoning

FloydNet introduces a learning paradigm that maintains ordered pair states and updates target relations by attending over candidate pairs, inspired by the Floyd–Warshall algorithm. The Pivotal Attention mechanism learns relation composition and pivot weighting in parallel, extending to k-tuples in the ζNet framework. Experiments show ζNet achieves high accuracy on CLRS-30 and near-optimal performance on non-metric TSP instances, matching the discriminative power of k-FWL on BREC.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 31

THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model

arXiv:2607. 27303v1 Announce Type: new Abstract: Temporal heterogeneous graphs offer a natural abstraction for dynamic relational systems in which diverse node and relation types co-exist and evolve over time.

By Yixin Peng, Diego Collarana, Er Jin, Stefan Decker

llms benchmarks

arXiv AI

Sep 16

Thinking Deeper, Not Longer: Memory-Efficient Test-Time Reasoning with Depth-Recurrent Transformers for Compositional Generalization

arXiv:2603.21676v2 Announce Type: replace-cross Abstract: Standard Transformers have a fixed computational depth, limiting their ability to generalize to tasks that require variable-depth reasoning....

By Hung-Hsuan Chen

llms safety

arXiv Machine Learning

Aug 13

AutoGrable: What Is a Good Graph for a Table?

arXiv:2608. 11431v1 Announce Type: new Abstract: Graph learning presupposes a graph, and tables and relational databases do not come with one.

By Tamara Cucumides, Floris Geerts

safety

arXiv Machine Learning

Jun 2

Chaining 2-FWL GNNs for Combinatorial Graph Alignment

arXiv:2510. 03086v2 Announce Type: replace Abstract: For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly initialized FAQ remains a strong classical baseline, while existing GNN approaches struggle in the purely structural setting.

By Marc Lelarge

rag benchmarks safety

arXiv Machine Learning

Jun 18

Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning

arXiv:2606. 15633v2 Announce Type: replace Abstract: Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs).

By Donald Loveland, Puja Trivedi, Ari Weinstein, Edward W Huang, Danai Koutra

llms rag benchmarks

arXiv AI

2d ago

Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning

arXiv:2609.33149v2 Announce Type: replace Abstract: A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how...

By Hongbo Chen, Guohua Lu, Ting Dang, Hong Jia

llms fine-tuning

One email a morning, machine-written

Related stories

THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model

Thinking Deeper, Not Longer: Memory-Efficient Test-Time Reasoning with Depth-Recurrent Transformers for Compositional Generalization

AutoGrable: What Is a Good Graph for a Table?

Chaining 2-FWL GNNs for Combinatorial Graph Alignment

Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning

Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning